Flow annealed importance sampling bootstrap
Normalizing flows are tractable density models that can approximate complicated target
distributions, eg Boltzmann distributions of physical systems. However, current methods for …
distributions, eg Boltzmann distributions of physical systems. However, current methods for …
Deep Generative Models, Synthetic Tabular Data, and Differential Privacy: An Overview and Synthesis
This article provides a comprehensive synthesis of the recent developments in synthetic
data generation via deep generative models, focusing on tabular datasets. We specifically …
data generation via deep generative models, focusing on tabular datasets. We specifically …
Learning to Transform for Generalizable Instance-wise Invariance
Computer vision research has long aimed to build systems that are robust to transformations
found in natural data. Traditionally, this is done using data augmentation or hard-coding …
found in natural data. Traditionally, this is done using data augmentation or hard-coding …
Minimizing Convex Functionals over Space of Probability Measures via KL Divergence Gradient Flow
Motivated by the computation of the non-parametric maximum likelihood estimator (NPMLE)
and the Bayesian posterior in statistics, this paper explores the problem of convex …
and the Bayesian posterior in statistics, this paper explores the problem of convex …
Some challenges of calibrating differentiable agent-based models
Agent-based models (ABMs) are a promising approach to modelling and reasoning about
complex systems, yet their application in practice is impeded by their complexity, discrete …
complex systems, yet their application in practice is impeded by their complexity, discrete …
Normalizing Flows on the Product Space of SO (3) Manifolds for Probabilistic Human Pose Modeling
Normalizing flows have proven their efficacy for density estimation in Euclidean space but
their application to rotational representations crucial in various domains such as robotics or …
their application to rotational representations crucial in various domains such as robotics or …
Improved multifidelity Monte Carlo estimators based on normalizing flows and dimensionality reduction techniques
We study the problem of multifidelity uncertainty propagation for computationally expensive
models. In particular, we consider the general setting where the high-fidelity and low-fidelity …
models. In particular, we consider the general setting where the high-fidelity and low-fidelity …
Squared neural families: a new class of tractable density models
R Tsuchida, CS Ong… - Advances in neural …, 2024 - proceedings.neurips.cc
Flexible models for probability distributions are an essential ingredient in many machine
learning tasks. We develop and investigate a new class of probability distributions, which we …
learning tasks. We develop and investigate a new class of probability distributions, which we …
One-line-of-code data mollification improves optimization of likelihood-based generative models
Abstract Generative Models (GMs) have attracted considerable attention due to their
tremendous success in various domains, such as computer vision where they are capable to …
tremendous success in various domains, such as computer vision where they are capable to …
InvertibleNetworks. jl: A Julia package for scalable normalizing flows
InvertibleNetworks. jl is a Julia package designed for the scalable implementation of
normalizing flows, a method for density estimation and sampling in high-dimensional …
normalizing flows, a method for density estimation and sampling in high-dimensional …